Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 116 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.8447. Min Act: -0.1700

Data Index: 1097651 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.7978. Min Act: -0.1700

Data Index: 332896 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.8447. Min Act: -0.1700

Data Index: 1201745 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.8916. Min Act: -0.1700

Data Index: 1106111 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.8447. Min Act: -0.1700

Data Index: 1112059 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.8603. Min Act: -0.1700

Data Index: 945711 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.8291. Min Act: -0.1700

Data Index: 566383 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.8447. Min Act: -0.1700

Data Index: 770345 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.7978. Min Act: -0.1700

Data Index: 487201 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.7509. Min Act: -0.1700

Data Index: 748537 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.7665. Min Act: -0.1700

Data Index: 546030 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.7196. Min Act: -0.1700

Data Index: 1330366 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.7665. Min Act: -0.1700

Data Index: 131829 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.7509. Min Act: -0.1700

Data Index: 475571 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.7665. Min Act: -0.1700

Data Index: 1253211 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.7039. Min Act: -0.1700

Data Index: 1099400 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.6570. Min Act: -0.1700

Data Index: 783553 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.7039. Min Act: -0.1700

Data Index: 794617 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.7196. Min Act: -0.1700

Data Index: 1227380 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 3.8916. Min Range: -3.8916

Max Act: 3.7665. Min Act: -0.1700

Data Index: 1006749 (C4 (Web Text))

Max Activating Token Index: 816